Abstract: Neural network is a blackbox model whose learned knowledge is concealed in a large amount of connections. This has not only weakened the confidence of users in building intelligent systems using neural computing techniques, but also hindered the application of neural networks to data mining. Since extracting rules from neural networks help to solve those problems, this area has become a hot topic in both machine learning and neural computing communities. In this paper, the history of rule extraction from neural networks is introduced, the state-of-the-art of this field is surveyed, some controversies are discussed, and some issues valuable for future exploration in this area is indicated.